AI News

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward (arxiv.org)

Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative (arxiv.org)

Coupled Local and Global World Models for Efficient First Order RL (arxiv.org)

vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models (arxiv.org)

Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach (arxiv.org)

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning (arxiv.org)

Introduction to optimization methods for training SciML models (arxiv.org)

FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments (arxiv.org)

Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning (arxiv.org)

A Robust Optimization Approach to Sparse Principal Component Analysis (arxiv.org)

Few-Shot Prediction for Pulsar Noise with Long Short-Term Memory Network (arxiv.org)

Set-Preserving Calibration from Conformal P-Values to E-Values (arxiv.org)

Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning (arxiv.org)

Text-attributed Graph Condensation via Text Selection and Attribute Matching (arxiv.org)

An Asymptotic Theory of Chain-of-Thought in In-Context Learning (arxiv.org)

Local and Global Contraction Principles for MCMC Mixing (arxiv.org)

Analytical Evaluation of DCA Convergence Properties for Minimizing Prediction Functions of Gaussian RBF Support Vector Regression (arxiv.org)

Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection (arxiv.org)

Online Learning with Gradient-Variation Interval Regret (arxiv.org)

Phantom Transfer: Data Poisoning can Survive Data-Level Defences (arxiv.org)

Neural Networks Provably Learn Spectral Representations for Group Composition (arxiv.org)

PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers (arxiv.org)

Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference (arxiv.org)

Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings (arxiv.org)

High-Precision APT Malware Attribution with Out-of-Scope Resilience (arxiv.org)

Generating Rectifiable Measures through Neural Networks (arxiv.org)

Physics-informed diffusion models in spectral space (arxiv.org)

Analyzing Stream Collapse in Hyper-Connections: From Diagnosis to Mitigation (arxiv.org)

Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals (arxiv.org)

Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks (arxiv.org)

FinStressTS: A Parametric Synthetic Benchmark for Time-Series Forecasting in Finance (arxiv.org)

AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification (arxiv.org)

Inducing Reasoning Primitives from Agent Traces (arxiv.org)

WISE-HAR: A Generalizable Ensemble Deep Learning Framework for WiFi-Based Human Activity Recognition (arxiv.org)

Validation-Gated Multi-Agent Governance for Online Adaptation of Thermal-Hydraulic Surrogate Models under Operating-Regime Shift (arxiv.org)

Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics (arxiv.org)

GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory (arxiv.org)

RogueMerge: Robust and Unified Attacks against LLM Model Merging (arxiv.org)

Localized, High-resolution Geographic Representations with Slepian Functions (arxiv.org)

Multi-Modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinical Alzheimer Classification (arxiv.org)

From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting (arxiv.org)

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees (arxiv.org)

RRISE: Robust Radius Inference via a Surrogate Estimator (arxiv.org)

ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models (arxiv.org)

Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs (arxiv.org)

DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration (arxiv.org)

CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive Driving (arxiv.org)

Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning (arxiv.org)

Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models (arxiv.org)

The Violation Situation Pattern: A Knowledge-Graph Pattern for Compliance Violations (arxiv.org)